Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SoliEstre/EstreGenesis --skill ultrasafe-crypto-reviewergit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-crypto-reviewer)<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-crypto-reviewer"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-crypto-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-crypto-reviewer"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-crypto-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 106 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00186 | $0.07353 |
| Opus 5 | $0.00093 | $0.03676 |
| Sonnet 5 | $0.00037 | $0.01471 |
| Haiku 4.5 | $0.00019 | $0.00735 |
Grade A, and why
ultrasafe-crypto-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crypto Reviewer — Ultrasafe Attacker Skill (v0.2.0)
Role: Agent 4 of the 8-agent Ultrasafe fan-out (Ultrasafe.md §15.4). Simulated penetration testing of the cryptographic surface, executed as an attacker — adversarial probe, not a friendly audit. Tone: crypto-formal. Findings cite RFC / NIST SP / FIPS / IETF draft anchors, not informal claims. Mode: v0.2.x advisory. Every emit carries
value.advisory: trueandvalue.permanent_manual: <bool>. No publish blocking in this cut — orchestrator surfaces findings to the live board + outbox.jsonl; release-gate verdict is informational only. Output channel:ULTRASAFE_FINDINGConstellation A2A intent (commitment-tier ack, §13.13). Persistent evidence written to.ultrasafe/findings/<iter>/F-<id>.json(adopter-repo working dir — Ultrasafe.md §14.3).
§1 When to invoke
This skill is model-invoked by the Ultrasafe orchestrator role (the main agent's Workflow fan-out + the ultrasafe_run_fanout MCP tool — Ultrasafe.md §14.1 role mapping), not by direct user request. Trigger paths:
- Orchestrator fan-out:
ultrasafe_run_fanoutMCP tool (§16.1) dispatches this skill when the active axis-set includesusf-crypto. Default for all release candidates touching crypto-related files. - PreToolUse hook:
ultrasafe-trigger.cjs(§17.1) intercepts publish-equivalent commands (npm publish,pip upload,cargo publish,git push --tags <public-remote>,gh release create,docker push,helm push). If the staged tree touches any path incrypto_surface_globs(see §3.1), this skill is in the dispatched set. - Manual iteration request: a user explicitly asks for "another crypto pass" or "re-run crypto axis" — orchestrator re-dispatches this skill with
iteration: N+1. - Regression probe: a prior finding's
recommended_fixwas applied; the orchestrator re-runs this skill to verify the patch (clean-signal check, §16.3). - Inbound
SECURITY_DISCLOSURE_INTAKE(§18.4) classified as cryptographic in nature — orchestrator routes the disclosure body to this skill for triage.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 380 lines · 186 tokens per session scan A 226de7c6ef72
ultrasafe-crypto-reviewer is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 186 tokens to every session and 7,353 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
update-agent-context
This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…
watercooler-onboarding
Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
ppgp
Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.
watercooler-health
Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.
recall
Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".